© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 2573
    Prev
    Next
    INDEX
    Explanations

    measurements of bond lengths in angstroms

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    RSpec
    -0.74
    Šaltiniai
    -0.70
    expandindo
    -0.68
    رشف
    -0.68
     Sard
    -0.68
    protoimpl
    -0.67
    Viited
    -0.67
    adto
    -0.67
     Benson
    -0.66
    ----+
    -0.66
    POSITIVE LOGITS
    Å
    2.70
     Å
    2.47
     å
    0.83
    Å
    0.81
    Ä
    0.73
    ̊
    0.69
    ChildScrollView
    0.60
     visualiser
    0.60
    Ǻ
    0.54
     Ä
    0.54
    Activations Density 0.002%

    No Known Activations